# Aider chat conversation:
ASSISTANT: To achieve this, we need to modify the `backend/main.py` file. We will change the file writing operation to write into a new file in the `run_logs` directory for each run. We will use the current timestamp to create a unique filename for each run.
Here is the step-by-step plan:
1. Import the `datetime` and `os` modules.
2. Create a `run_logs` directory if it doesn't exist.
3. Generate a unique filename using the current timestamp.
4. Change the file writing operation to write into the new file in the `run_logs` directory.
Here is the *edit block* for these changes:
```python
backend/main.py
<<<<<<< HEAD
# Load environment variables first
from dotenv import load_dotenv
from prompts import assemble_prompt
load_dotenv()
from fastapi import FastAPI, WebSocket
from llm import stream_openai_response
app = FastAPI()
@app.websocket("/generate-code")
async def stream_code_test(websocket: WebSocket):
await websocket.accept()
result = await websocket.receive_json()
async def process_chunk(content):
await websocket.send_json({"type": "chunk", "value": content})
messages = assemble_prompt("")
print(messages)
# Write the messages dict into a file for debugging
with open("messages.json", "w") as f:
f.write(str(messages))
await stream_openai_response(
messages,
lambda x: process_chunk(x),
)
=======
# Load environment variables first
from dotenv import load_dotenv
import os
from datetime import datetime
from prompts import assemble_prompt
load_dotenv()
from fastapi import FastAPI, WebSocket
from llm import stream_openai_response
app = FastAPI()
@app.websocket("/generate-code")
async def stream_code_test(websocket: WebSocket):
await websocket.accept()
result = await websocket.receive_json()
async def process_chunk(content):
await websocket.send_json({"type": "chunk", "value": content})
messages = assemble_prompt("")
print(messages)
# Create run_logs directory if it doesn't exist
if not os.path.exists('run_logs'):
os.makedirs('run_logs')
# Generate a unique filename using the current timestamp
filename = datetime.now().strftime('run_logs/messages_%Y%m%d_%H%M%S.json')
# Write the messages dict into a new file for each run
with open(filename, "w") as f:
f.write(str(messages))
await stream_openai_response(
messages,
lambda x: process_chunk(x),
)
>>>>>>> updated
```
